{"id":"W4403785816","doi":"10.1016/j.joi.2025.101759","title":"WISDOM: An AI-powered framework for emerging research detection using weak signal analysis and advanced topic modelling","year":2025,"lang":"en","type":"preprint","venue":"Journal of Informetrics","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Defence Research and Development Canada; National Research Council Canada","funders":"","keywords":"SIGNAL (programming language); Computer science; Detection theory; Data science; Artificial intelligence; Telecommunications","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01350452,0.00165803,0.002223715,0.009126758,0.002040765,0.008276497,0.003364322,0.003362417,0.007728137],"category_scores_gemma":[0.05813561,0.0008936432,0.002769443,0.005914059,0.002845972,0.009846504,0.007758322,0.004420588,0.003264869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001495071,"about_ca_system_score_gemma":0.003745015,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002335398,"about_ca_topic_score_gemma":0.003312553,"domain_scores_codex":[0.9933537,0.003223697,0.0004928424,0.001187012,0.001466968,0.0002758142],"domain_scores_gemma":[0.9671735,0.02336145,0.001859748,0.003608695,0.002676515,0.00132019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003333448,0.0001579283,0.003933563,0.000767724,0.00037083,0.0003141904,0.001137685,0.02926953,0.00247832,0.6382527,0.018759,0.3042252],"study_design_scores_gemma":[0.00003491446,0.00004003334,0.0004381434,0.00009019604,0.00006255162,0.0001169481,0.0001447969,0.2361391,0.0008144187,0.7508931,0.01118547,0.00004051637],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00161037,0.0004229024,0.9931582,0.001127786,0.0001353668,0.00008179925,0.0005204907,0.001066644,0.001876483],"genre_scores_gemma":[0.1174406,0.0009547513,0.8711008,0.0008230525,0.0009398901,0.0006152386,0.001664028,0.0004750792,0.005986622],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9908732,"threshold_uncertainty_score":0.0714196,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2034003105124179,"score_gpt":0.525670070531794,"score_spread":0.3222697600193761,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}